Skip to main content
Add long-term memory to OpenClaw agents with the @mem0/openclaw-mem0 plugin. Your agent forgets everything between sessions — this plugin fixes that by automatically watching conversations, extracting what matters, and bringing it back when relevant.

​
Overview

OpenClaw Mem0 Architecture
The plugin provides:
  1. Auto-Recall — Before the agent responds, memories matching the current message are injected into context
  2. Auto-Capture — After the agent responds, the exchange is sent to Mem0 which decides what’s worth keeping
  3. Agent Tools — Five tools for explicit memory operations during conversations
Both auto-recall and auto-capture run silently with no manual configuration required.

​
Installation

openclaw plugins install @mem0/openclaw-mem0

​
Setup and Configuration

​
Platform Mode (Mem0 Cloud)

Get your API key from app.mem0.ai.
Add to your openclaw.json: 
// plugins.entries
"openclaw-mem0": {
  "enabled": true,
  "config": {
    "apiKey": "${MEM0_API_KEY}",
    "userId": "your-user-id"
  }
}

​
Open-Source Mode (Self-hosted)

No Mem0 key needed. Requires OPENAI_API_KEY for default embeddings/LLM. 
"openclaw-mem0": {
  "enabled": true,
  "config": {
    "mode": "open-source",
    "userId": "your-user-id"
  }
}
Sensible defaults work out of the box. To customize the embedder, vector store, or LLM: 
"config": {
  "mode": "open-source",
  "userId": "your-user-id",
  "oss": {
    "embedder": { "provider": "openai", "config": { "model": "text-embedding-3-small" } },
    "vectorStore": { "provider": "qdrant", "config": { "host": "localhost", "port": 6333 } },
    "llm": { "provider": "openai", "config": { "model": "gpt-4o" } }
  }
}
All oss fields are optional. See Mem0 OSS docs for available providers.

​
Short-term vs Long-term Memory

Memories are organized into two scopes:
  • Session (short-term) — Auto-capture stores memories scoped to the current session via Mem0’s run_id / runId parameter. These are contextual to the ongoing conversation.
  • User (long-term) — The agent can explicitly store long-term memories using the memory_store tool (with longTerm: true, the default). These persist across all sessions for the user.
During auto-recall, the plugin searches both scopes and presents them separately — long-term memories first, then session memories — so the agent has full context.

​
Agent Tools

The agent gets five tools it can call during conversations:
ToolDescription
memory_searchSearch memories by natural language
memory_listList all stored memories for a user
memory_storeExplicitly save a fact
memory_getRetrieve a memory by ID
memory_forgetDelete by ID or by query
The memory_search and memory_list tools accept a scope parameter ("session", "long-term", or "all") to control which memories are queried. The memory_store tool accepts a longTerm boolean (default: true) to choose where to store.

​
CLI Commands

# Search all memories (long-term + session)
openclaw mem0 search "what languages does the user know"

# Search only long-term memories
openclaw mem0 search "what languages does the user know" --scope long-term

# Search only session/short-term memories
openclaw mem0 search "what languages does the user know" --scope session

# View stats
openclaw mem0 stats

​
Configuration Options

​
General Options

KeyTypeDefaultDescription
mode"platform" | "open-source""platform"Which backend to use
userIdstring"default"Scope memories per user
autoRecallbooleantrueInject memories before each turn
autoCapturebooleantrueStore facts after each turn
topKnumber5Max memories per recall
searchThresholdnumber0.3Min similarity (0–1)

​
Platform Mode Options

KeyTypeDefaultDescription
apiKeystring—Required. Mem0 API key (supports ${MEM0_API_KEY})
orgIdstring—Organization ID
projectIdstring—Project ID
enableGraphbooleanfalseEntity graph for relationships
customInstructionsstring(built-in)Extraction rules — what to store, how to format
customCategoriesobject(12 defaults)Category name → description map for tagging

​
Open-Source Mode Options

KeyTypeDefaultDescription
customPromptstring(built-in)Extraction prompt for memory processing
oss.embedder.providerstring"openai"Embedding provider ("openai", "ollama", etc.)
oss.embedder.configobject—Provider config: apiKey, model, baseURL
oss.vectorStore.providerstring"memory"Vector store ("memory", "qdrant", "chroma", etc.)
oss.vectorStore.configobject—Provider config: host, port, collectionName, dimension
oss.llm.providerstring"openai"LLM provider ("openai", "anthropic", "ollama", etc.)
oss.llm.configobject—Provider config: apiKey, model, baseURL, temperature
oss.historyDbPathstring—SQLite path for memory edit history
Everything inside oss is optional — defaults use OpenAI embeddings (text-embedding-3-small), in-memory vector store, and OpenAI LLM.

​
Key Features

  1. Zero Configuration — Auto-recall and auto-capture work out of the box with no prompting required
  2. Dual Memory Scopes — Session-scoped short-term and user-scoped long-term memories
  3. Flexible Backend — Use Mem0 Cloud for managed service or self-host with open-source mode
  4. Rich Tool Suite — Five agent tools for explicit memory operations when needed

​
Conclusion

The @mem0/openclaw-mem0 plugin gives OpenClaw agents persistent memory with minimal setup. Whether using Mem0 Cloud or self-hosting, your agents can now remember user preferences, facts, and context across sessions automatically.

OpenAI Agents SDK

Build agents with OpenAI’s SDK and Mem0

LangGraph Integration

Create stateful agent workflows with memory